curl --request POST \
--url https://api.ephone.ai/suno/v2/sample \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"chop_sample_end_s": 30,
"chop_sample_start_s": 0,
"music_id": "track id"
}
'import requests
url = "https://api.ephone.ai/suno/v2/sample"
payload = {
"chop_sample_end_s": 30,
"chop_sample_start_s": 0,
"music_id": "track id"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({chop_sample_end_s: 30, chop_sample_start_s: 0, music_id: 'track id'})
};
fetch('https://api.ephone.ai/suno/v2/sample', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.ephone.ai/suno/v2/sample"
payload := strings.NewReader("{\n \"chop_sample_end_s\": 30,\n \"chop_sample_start_s\": 0,\n \"music_id\": \"track id\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}{
"code": "success",
"message": "success",
"data": {
"task_id": "5adac6ee-..."
}
}{
"code": "error",
"message": "music_id is required"
}{
"error": {
"message": "Invalid Token",
"type": "rix_api_error"
}
}{
"error": {
"message": "Too many requests, please try again later",
"type": "rix_api_error"
}
}Sample Rework
Chop a sample and build a new track around it.
curl --request POST \
--url https://api.ephone.ai/suno/v2/sample \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"chop_sample_end_s": 30,
"chop_sample_start_s": 0,
"music_id": "track id"
}
'import requests
url = "https://api.ephone.ai/suno/v2/sample"
payload = {
"chop_sample_end_s": 30,
"chop_sample_start_s": 0,
"music_id": "track id"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({chop_sample_end_s: 30, chop_sample_start_s: 0, music_id: 'track id'})
};
fetch('https://api.ephone.ai/suno/v2/sample', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.ephone.ai/suno/v2/sample"
payload := strings.NewReader("{\n \"chop_sample_end_s\": 30,\n \"chop_sample_start_s\": 0,\n \"music_id\": \"track id\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}{
"code": "success",
"message": "success",
"data": {
"task_id": "5adac6ee-..."
}
}{
"code": "error",
"message": "music_id is required"
}{
"error": {
"message": "Invalid Token",
"type": "rix_api_error"
}
}{
"error": {
"message": "Too many requests, please try again later",
"type": "rix_api_error"
}
}POST /v1/task/submit with model set to suno/sample and the parameters inside input. Both behave and bill the same.Task result
What the fetch result holds once the task succeeds
Task result
What the fetch result holds once the task succeeds
data.musics holds the tracks it produced, 2 per run. On partial success you are billed for the tracks that actually succeeded.{
"code": "success",
"data": {
"task_id": "5adac6ee-...",
"action": "sample",
"model": "suno/sample",
"status": "SUCCESS",
"progress": "100%",
"submit_time": 1757800000000,
"finish_time": 1757800120000,
"musics": [
{
"music_id": "89b20862-...",
"title": "Rain on Tin Roof",
"tags": "lo-fi piano",
"audio_url": "https://...",
"image_url": "https://...",
"duration": 187.56
}
]
}
}
Authorizations
Send your API key in the Authorization: Bearer YOUR_API_KEY header.
Body
Source Track: The track to work on. Use the music_id from an earlier result.
Sample From: Where the sample starts, in seconds.
Sample To: Where the sample ends, in seconds.
Model Version: All three versions are priced the same; pick by the style you want. Options: chirp-v6 v6 (default); chirp-v6-wild v6 Wild (bolder); chirp-v6-mini v6 Mini (faster).
chirp-v6, chirp-v6-wild, chirp-v6-mini Custom Mode: Off: describe the song in one line. On: supply your own full lyrics.
Instrumental: Produce music without any vocals.
Inspiration Prompt: One line describing the song you want. Required when custom mode is off. Up to 3000 characters.
Lyrics: Full lyrics, up to 5000 characters. Use markers like [Verse] and [Chorus] to shape the structure.
Title: Track title, up to 80 characters.
Style Tags: The style you want, e.g. 'lo-fi piano, mellow, rain'. Up to 1000 characters.
Avoid These Styles: Styles to steer away from.
Style Weight: 0 to 1. Higher sticks closer to your style tags; lower leaves more room to improvise.
Weirdness: 0 to 1. Higher yields more unexpected results; lower stays conventional.
Audio Weight: 0 to 1. How strongly the reference audio shapes the result.
Polish Lyrics: Rewrites your lyrics to sing better. Custom mode only.
Vocal Gender: Voice gender of the singer. Options: Male Male; Female Female.
Male, Female Variety: How far the result may drift from the style you specified. Options: off Exact; normal Balanced; high Varied; extra Bold; max Maximum.
off, normal, high, extra, max Max Quality: Spend more compute to keep the whole song coherent. Custom mode only; doubles the price.
Custom Model: Generate with a model you trained. Use the model_id from a create-model result. Cannot be combined with persona_id.
Output Format: Format of the finished audio. Defaults to mp3. Options: mp3 MP3 (common); m4a M4A; wav WAV (lossless).
mp3, m4a, wav Notify hook: when the task ends, the same content as the fetch result is POSTed to this URL (a public http / https URL). Omit it to poll instead.
Was this page helpful?